Federated Learning in Prediction of Dementia Stage: An Experimental Study
Boyun Eom, Muhammad Zubair, Dong-Hwan Park, Hyunhak Kim, Young‐Ho Suh, Sunhwan Lim, Chan‐Won Park · 2023
Federated Learning(FL) has emerged as the optimal approach for training machine learning models when dealing with data containing sensitive information, making data sharing impractical. Particularly in contexts where privacy is a primary concern, such as medical applications, Federated Learning demonstrates its efficacy as a solution. Motivated by this, we have conducted comprehensive experiments using a medical image dataset. One of the key objectives of these experiments is to evaluate the influence of Non-IID data which is frequently encountered in Federated Learning, especially within the medial field. We present our exploration of Federated Learning in classification of OASIS medical images, along with the results obtained from various experiments.